- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes a two-stage post-training framework to improve visual reasoning with efficient inference. In stage I, it uses supervised fine-tuning with region-level evidence supervision at visual-token positions. In stage II, it conducts reinforcement learning combining task rewards with contrastive rewards derived from original images and additional perturbed images. Experiments show that VISER outperforms the compared methods on five image VQA benchmarks, with inference latency close to the base model on VStar. Analyses show that after stage II training, it yields fewer errors under background perturbations but becomes less sensitive to visual evidence corruption.
Critical strengths
- The paper addresses an important practical problem, which is improving visual reasoning without substantially increasing inference cost.
- The empirical evaluation is comprehensive, as it includes comparisons with multiple baselines and ablations of the training stages and reward components. These experiments clarify the contribution of the main design choices.
Critical weaknesses
- The incremental benefit of the contrastive rewards is modest. The full reward improves the five-benchmark average by 0.63 points over task-reward-only RL, while individual reward components even regress on some benchmarks. Moreover, the intervention analysis doesn't show increased sensitivity to evidence corruption after stage II (the evidence-corruption CDR decreases from 27.11% to 25.56%).
Questions for authors
- Have the authors checked TreeVGR-RL-37K for overlap with the VStar test set? A public report has raised a possible overlap here. If it exists, could the authors provide decontaminated VStar results?
- The latency comparison is reported only on VStar. Since inference efficiency is vital for the paper, could the authors report corresponding latency results on the remaining image VQA and high-resolution benchmarks?
- Could the authors provide an analysis of representative failure cases? It may help understand when evidence-focused post-training is beneficial.